{ "openapi": "3.0.1", "info": { "title": "cBioPortal Cancer Genomics Extractor", "description": "Point at ANY cBioPortal instance (the MSKCC flagship, BCGSC, GENIE, institutional mirrors) and pull cancer-genomics metadata: studies, the OncoTree cancer-type taxonomy, molecular profiles, and genes. One actor, the whole cBioPortal REST API, every row lossless.", "version": "0.1", "x-build-id": "NZrMpDu1g5P2hcd2q" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/datamule~cbioportal-cancer-genomics-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-datamule-cbioportal-cancer-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/datamule~cbioportal-cancer-genomics-extractor/runs": { "post": { "operationId": "runs-sync-datamule-cbioportal-cancer-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/datamule~cbioportal-cancer-genomics-extractor/run-sync": { "post": { "operationId": "run-sync-datamule-cbioportal-cancer-genomics-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "server": { "title": "cBioPortal base URL", "type": "string", "description": "The base URL of ANY cBioPortal instance. ONE actor speaks to all of them — the MSKCC public flagship (https://www.cbioportal.org), the BC Genome Sciences Centre mirror (https://cbioportal.bcgsc.ca), GENIE, and dozens of institutional deployments, because every install exposes the identical Swagger-generated REST API. You can pass the bare host, an https URL, a proxied path prefix, or a URL ending in /api — the actor normalises it. Required unless you use \"Servers\" below." }, "servers": { "title": "Servers (query several instances at once)", "type": "array", "description": "Optional: run the SAME mode across multiple cBioPortal instances at once (the flagship plus institutional mirrors, say). Each output row is tagged with its _server. Use this OR the single \"cBioPortal base URL\" above (at least one is required). A server that is unreachable, auth-gated (401/403), or returns a non-JSON body is skipped with a warning and the batch continues; if EVERY server is skipped the run fails fast.", "items": { "type": "string" } }, "mode": { "title": "What to extract", "enum": [ "studies", "cancerTypes", "study-detail", "molecular-profiles", "genes" ], "type": "string", "description": "Which cBioPortal collection to pull. 'studies' = one row per cancer study (the default). 'cancerTypes' = the portal's cancer-type / OncoTree taxonomy. 'study-detail' = the DETAILED record (all per-datatype sample counts) for the one study named in 'Study ID'. 'molecular-profiles' = molecular profiles, either portal-wide or (if 'Study ID' is set) for one study. 'genes' = the portal's gene table (Entrez ID + HUGO symbol).", "default": "studies" }, "studyId": { "title": "Study ID", "type": "string", "description": "A cBioPortal study identifier, e.g. 'acbc_mskcc_2015' or 'brca_tcga_pan_can_atlas_2018'. REQUIRED for mode 'study-detail'. OPTIONAL for mode 'molecular-profiles' — when set, only that study's profiles are returned; when empty, the portal-wide profile list is returned. Ignored for the other modes." }, "pageSize": { "title": "Page size", "minimum": 1, "maximum": 100000, "type": "integer", "description": "How many records to request per API page (default 500). cBioPortal honours pageSize everywhere; the actor paginates defensively and de-duplicates, so this mainly tunes request size. Larger pages = fewer round-trips." }, "maxRecords": { "title": "Max records (global cap)", "minimum": 1, "type": "integer", "description": "A GLOBAL cap on the number of rows emitted across ALL servers (each row is one billable event). Reached mid-collection, the run stops deterministically. Leave empty to emit the entire collection from every reachable server. Useful to keep a first test run cheap." }, "userAgent": { "title": "User-Agent override", "type": "string", "description": "Optional override for the request User-Agent. A descriptive User-Agent is sent by default — some data centres throttle or reject a blank / generic UA. Only override if a specific instance asks you to identify differently." }, "timeoutSecs": { "title": "Read timeout (seconds)", "minimum": 1, "maximum": 900, "type": "integer", "description": "How long to wait for the server to answer each request (default 120). Large gene / study lists can be slow; servers also enforce their own timeouts." }, "bearer": { "title": "Bearer token", "type": "string", "description": "Optional bearer token for an auth-gated cBioPortal deployment (sent as Authorization: Bearer ***). NOT required for the public flagship or BCGSC. Never logged." }, "extraHeaders": { "title": "Extra request headers", "type": "object", "description": "Optional extra HTTP headers as a JSON object, e.g. {\"X-Api-Key\": \"...\"} for a gateway-fronted instance. Not required for public servers. Header values are never logged." } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 } } } } } } } } } }